Discrete Factorization Machines for Fast Feature-based Recommendation
This work addresses fast and accurate recommendation for mobile applications with limited computational resources, representing an incremental improvement through binarization techniques.
The paper tackles the problem of high storage and computational costs in feature-based recommendation systems by introducing Discrete Factorization Machines (DFM), which binarize model parameters to enable efficient operations. DFM outperforms state-of-the-art binarized models and shows competitive performance with its real-valued counterpart, reducing quantization loss effectively.
User and item features of side information are crucial for accurate recommendation. However, the large number of feature dimensions, e.g., usually larger than 10^7, results in expensive storage and computational cost. This prohibits fast recommendation especially on mobile applications where the computational resource is very limited. In this paper, we develop a generic feature-based recommendation model, called Discrete Factorization Machine (DFM), for fast and accurate recommendation. DFM binarizes the real-valued model parameters (e.g., float32) of every feature embedding into binary codes (e.g., boolean), and thus supports efficient storage and fast user-item score computation. To avoid the severe quantization loss of the binarization, we propose a convergent updating rule that resolves the challenging discrete optimization of DFM. Through extensive experiments on two real-world datasets, we show that 1) DFM consistently outperforms state-of-the-art binarized recommendation models, and 2) DFM shows very competitive performance compared to its real-valued version (FM), demonstrating the minimized quantization loss. This work is accepted by IJCAI 2018.